间歇过程的统计建模与在线监测

被引:57
作者
陆宁云 [1 ]
王福利
高福荣 [2 ]
王姝
机构
[1] 香港科学技术大学化学工程系 
[2] 香港科学技术大学化学工程 
关键词
间歇过程; 多元统计模型; 过程监测; 主成分分析; 偏最小二乘; 三线性分解模型;
D O I
10.16383/j.aas.2006.03.011
中图分类号
TP277 [监视、报警、故障诊断系统];
学科分类号
0804 ; 080401 ; 080402 ;
摘要
现代过程工业正逐渐倚重于生产小批量、多品种、高附加值产品的间歇过程.基于多元统计模型的过程监测是保障生产安全和产品质量的重要工具.从间歇过程独特的数据特性出发,将现有的多元统计建模方法进行合理的分类,简要回顾了各类方法的起源、发展及延伸的历程.除了阐述每种方法的基本原理,还详细讨论了各种方法的适用背景,相互关联及优缺点等内容,并对这一领域中依然存在的问题以及研究前景给出中肯的评述.
引用
收藏
页码:400 / 410
页数:11
相关论文
共 47 条
[1]  
Nonlinear principal component analysis based on principal curves and neural network. Dong D,d McAvoy T J. Computers and Chemistry . 1996
[2]  
Monitoring batch processes using multiway principal component analysis. Nomikos P,MacGregor J F. American Institute of Chemical Engineers. AIChE Journal . 1994
[3]  
A method for predicting future observations in the monitoring of a batch process. Cho H W,Kim K J. Journal of Environmental Quality . 2003
[4]  
Partial least squares regression: A tutorial. Geladi P,Kowalshi B R. Analytica Chimica Acta . 1986
[5]  
A User’s Guide to Principal Components. Jackson J E. . 1991
[6]  
Synchronization of batch trajectories using dynamic time warping. Kassidas A,MacGregor J F,Taylor P A. American Institute of Chemical Engineers. AIChE Journal . 1998
[7]  
Adaptive batch monitoring using hierarchical PCA. Rannar S,MacGregor J F,Wold S. Chemometrics and Intelligent Laboratory Systems . 1998
[8]  
Critical evaluation of approaches for on-line batch process monitoring. Van Sprang E N M,Ramaker H J,Westerhuis J A,Gurden S P,Smilde A K. Chemical Engineering Science . 2002
[9]  
An overview of multivariate statistical process control in continuous and batch process performance monitoring. Martin E B,Morris A J. Transactions of the Institute of Measurement and Control . 1996
[10]  
Improved DTW algorithms for synchronization of batch trajectories. Gao X,Wang G,Zhao L J,Ma J H. Information and Control . 2001